Describe the image you want to create
0/20000Advanced Settings
Tips for better results
- - Be specific about style, colors, and mood
- - Include lighting and composition details
- - Use artistic style references like "photorealistic" or "watercolor"
- - For image-to-image, upload multiple reference images for better results
- - Describe how you want to transform all uploaded images
- - If generation fails, try switching to a different model in the dropdown for different results and fewer restrictions
Make an explainer idea visible with Nano Banana 2.1
Give viewers a setting for the speaker and an image for the idea. On Vo Omni, prepare presenter backgrounds and concept stills that you can review alongside your narration notes.
Give each still one teaching purpose
Decide whether the image introduces the speaker, illustrates an object or clarifies a relationship. Keep the supporting scene from competing with that purpose.
Start from a script beat
Summarize the point the viewer needs to understand in a required prompt of up to 20,000 characters. Describe the subject, background and area reserved for captions; this page generates images, not narration.
Guide the scene with pictures
Upload up to 14 JPEG, PNG or WebP images, each no more than 30 MB. Use a room, object or presenter reference and describe what it should contribute. Check people and objects in the result against the source.
Fit the lesson’s visual format
Select the aspect ratio for the intended frame and choose 1K, 2K or 4K. Both JPG and PNG are available for images that you will place in your editing or presentation workflow.
Prepare the visual support for a spoken explanation
A presenter backdrop sets context; a concept illustration gives the audience something specific to inspect. Nano Banana 2.1 lets you request either as a still image. Build the prompt around one point from the script and review the output for distracting or misleading details.
The Vo Omni page opens Nano Banana 2.1 as its own model choice, separate from Nano Banana 2. Initial settings are 1K, Auto and JPG. It does not provide Google Search, so verify factual diagrams and explanatory content using your source material.
Room around the speaker
Ask for quiet space near the planned presenter position and avoid busy objects behind the head. Review the composition in the actual frame where the speaker will appear.
A visual metaphor needs review
An illustration of storage, flow or sorting can support an explanation, but generated symbols and object relationships may be wrong. Compare them with the point you intend to teach.
Plan the stills around the explanation
Choose the format and detail level after deciding how each image will be used with the script.
Count the image cost
For Vo Omni’s Nano Banana 2.1, 1K is 2 credits per image, 2K is 4, and 4K is 6. Reference images do not carry an extra fee.
Keep captions readable
Use 16:9 for a landscape lesson or 9:16 for a vertical explainer, with caption space described in the prompt. Check the resulting background behind your actual text.
Bring stills into the edit
Download the image and place it manually in your video editor. If a video model will use it as a reference, upload it separately after checking that model’s format, ratio and file restrictions.
Two images to support an explanation
These prompts focus on a speaker’s setting and a concrete visual analogy, leaving final text for the editing stage.
A calm background for a science presenter
Choose 16:9 and prompt: “An approachable science studio, soft off-white wall, a low shelf with a globe and two plain books on the left, gentle daylight, center-right kept uncluttered for a presenter, no people or writing, lower strip visually quiet for captions.” Check the shelf does not interfere with the planned speaker position.
Explain sorting with familiar objects
Try a 4:3 still: “Top-down illustration of twelve wooden blocks in three colors on a neutral table, one mixed group on the left and three visibly separated color groups on the right, simple editorial style, no arrows or text.” Count the objects and check the grouping before using it to explain sorting.
Prepare a still for one section of the script
Connect the prompt to the teaching point, then review the image in the lesson context.
Choose what the viewer should notice
Write one script point and decide whether it needs a background or an illustrative object. Add references only when they explain the speaker, setting or subject.
Leave room for the spoken content’s text
Specify the caption area, aspect ratio, 1K/2K/4K resolution and JPG/PNG format. Confirm credits before generating; exact labels can be added later.
Review with the narration notes
Sign in, generate and check the image against your explanation. Download the approved still for manual editing, and find the task again in My Creations if you need to revisit it.
Using stills in an explainer
What is the cost of an explainer still?
Vo Omni prices each Nano Banana 2.1 image by resolution: 2 credits for 1K, 4 for 2K and 6 for 4K. Uploading references adds no separate reference charge.
Can I use a presenter or room photo?
You can add up to 14 JPEG, PNG or WebP references, up to 30 MB each, and explain which person or room details matter. Inspect the output for changes to facial features, proportions and background details; a reference is not a guarantee of exact identity preservation.
Which aspect ratios fit lesson visuals?
Choose from 15 options: auto, 1:1, 2:3, 3:2, 1:4, 4:1, 3:4, 4:3, 4:5, 5:4, 1:8, 8:1, 9:16, 16:9 and 21:9. Match the ratio to the lesson layout, then separately select 1K, 2K or 4K.
Are generated diagrams ready to teach from?
Review them against reliable teaching material first. Counts, symbols, labels and spatial relationships can need correction. For an exact explanation, generate the illustrative base, then add verified labels and arrows in an editor.
Does this page create a talking presenter video?
It creates still images. Download the result for manual use in your video edit, or manually upload it to a suitable video model after checking the model’s input restrictions. A generated presenter image does not add speech or animation by itself.
Are failed illustration tasks refunded?
The generation credits are refunded after a task is confirmed failed. A delayed response or temporarily unavailable task-status query does not alone indicate failure. Recheck the existing task for its confirmed outcome.
Give the next script point a visual
Prepare a background or concept illustration with Nano Banana 2.1, then check that it supports what you want the audience to understand.